Podcast · 247 episodes
Latent Space: The AI Engineer Podcast, page 2
by Latent.Space · English
The podcast by and for AI Engineers! In 2025, over 10 million readers and listeners came to Latent Space to hear about news, papers and interviews in Software 3.0. We cover Foundation Models changing every domain in Code Generation, Multimodality, AI Agents, GPU Infra and more, directly from the founders, builders, and thinkers involved in pushing the cutting edge. Striving to give you both the definitive take on the Current Thing down to the first introduction to the tech you'll be using in the next 3 months! We break news and exclusive interviews from OpenAI, Anthropic, Gemini, Meta (Soumith Chintala), Sierra (Bret Taylor), tiny (George Hotz), Databricks/MosaicML (Jon Frankle), Modular (Chris Lattner), Answer.ai (Jeremy Howard), et al. Full show notes always on https://latent.space Sponsorship and business inquiries: business@latent.space www.latent.space
All episodes, page 2
🔬Scaling Past Informal AI - Carina Hong, Axiom MathVerified AI for “scaling brilliance” via formal verification and Lean.3 Jun 2026 · 1 h 33 min · 47 chapters
⚡️Satya Nadella: No Priors x Latent Space Crossover Special at Microsoft BuildSatya Nadella discusses Microsoft Build’s AI announcements, arguing for an “ecosystem play” where companies can participate as first-class participants by building their own AI using Microsoft’s…3 Jun 2026 · 39 min · 14 chapters
GitHub's plan for Agents — Kyle Daigle, GitHubGitHub’s plan for “agents” and how AI-driven workflows should work across Microsoft (Teams, Slack, email, GitHub) without forcing people to change how they work; also covers AI skills design,…2 Jun 2026 · 1 h 23 min · 31 chapters
Why Video Agent models are next — Ethan He, xAI Grok ImagineVideo agent models as the next step toward interactive, long-horizon generative video.1 Jun 2026 · 1 h 43 min · 43 chapters
The Age of Async Agents — Cognition's Walden Yan & OpenInspect's Cole MurrayThe “Age of Async Agents” and how background coding agents became practical in late 2025, focusing on architecture (brain vs machine), cloud execution, and the hard engineering needed for reliable…28 May 2026 · 1 h 8 min · 32 chapters
🔬ESM: The Bitter Lesson is Coming for Proteins - Alex Rives, BioHubAlex Rives (Biohub) argues for “scaling laws” in protein language modeling and describes ESMFold2/ESMC as a “world model” for protein sequence, structure, and function.27 May 2026 · 1 h 10 min · 37 chapters
Giving Agents Computers — Ivan Burazin, DaytonaDaytona’s evolution from early browser IDEs/hosting to “composable computers” for AI agents, focused on long-running, stateful “sandboxes” with very fast spin-up and high concurrency.21 May 2026 · 1 h 10 min · 38 chapters
Railway: The Agent-Native Cloud — Jake CooperRailway’s “agent-native cloud” approach to deploying and evolving software—especially for AI agents—by versioning infrastructure, safely rolling out changes, and scaling compute efficiently (cloud…20 May 2026 · 1 h 29 min · 55 chapters
The Autonomous Drone Tech Stack & Economics of Drones — Yaroslav Azhnyuk, The Fourth Law & Guest Host Noah Smith, NoahpinionHow drone warfare is shifting power toward software-defined, mass-producible autonomous systems; why the West is “not ready”; and the moral/ethical responsibilities of weapon makers.18 May 2026 · 1 h 59 min · 52 chapters
AI-Native Healthcare: 100M Doctor Visits, 10–20 Hours Saved, Prior Auth in Minutes — Janie Lee & Chai Asawa, AbridgeAbridge’s “AI-native healthcare” approach—an ambient clinical intelligence layer that listens to clinician-patient conversations to reduce documentation burden (10–20 hours/week), enable proactive…14 May 2026 · 1 h 5 min · 31 chapters
🔬Doing Vibe Physics — Alex Lupsasca, OpenAIAlex Lupsasca (OpenAI/Vanderbilt) explains how AI helped solve a theoretical physics problem about “single minus” gluon scattering amplitudes—previously believed to vanish—showing they are actually…5 May 2026 · 1 h 32 min · 40 chapters
Physical AI that Moves the World — Qasar Younis & Peter Ludwig, Applied IntuitionPhysical AI for safety-critical moving systems. Applied Intuition builds and sells technology (simulation, operating systems, and autonomy/fundamental AI) to automakers and governments to deploy…27 Apr 2026 · 1 h 12 min · 28 chapters
AIE Europe Debrief + Agent Labs Thesis: Unsupervised Learning x Latent Space Crossover Special (2026)Debrief from AI Europe and a crossover with Latent Space on the current AI ecosystem—especially “coding wars,” agent infrastructure, and the 2026 thesis that coding agents will “break containment” to…23 Apr 2026 · 55 min · 25 chapters
Shopify’s AI Phase Transition: 2026 Usage Explosion, Unlimited Opus-4.6 Token Budget, Tangle, Tangent, SimGym — with Mikhail Parakhin, Shopify CTOShopify’s internal “AI phase transition” in late 2025/early 2026—how employees adopted AI coding tools, how Shopify funds “unlimited” token budgets with model minimums (Opus-4.6), and how Shopify’s…22 Apr 2026 · 1 h 12 min · 41 chapters
🔬 Training Transformers to solve 95% failure rate of Cancer Trials — Ron Alfa & Daniel Bear, NoetikNoetic’s approach to training transformer-based “world models” on human tumor data to reduce cancer trial failure (claimed 90–95% fail) by improving patient selection rather than target/drug…20 Apr 2026 · 1 h 25 min · 37 chapters
Notion’s Token Town: 5 Rebuilds, 100+ Tools, MCP vs CLIs and the Software Factory Future — Simon Last & Sarah Sachs of NotionNotion’s “Token Town” discussion of building agentic products: Custom Agents, MCP vs CLIs, the “software factory” for automated coding workflows, and how Notion runs evals/agent platforms at…15 Apr 2026 · 1 h 17 min · 50 chapters
Extreme Harness Engineering for Token Billionaires: 1M LOC, 1B toks/day, 0% human code, 0% human review — Ryan Lopopolo, OpenAI Frontier & Symphony“Unharness Engineering” for deploying AI coding agents at scale using Codex harnesses and agent-driven SDLC automation (claims: “0% human code,” humans mostly post-merge; systems thinking; encode…7 Apr 2026 · 1 h 13 min · 40 chapters
Marc Andreessen introspects on The Death of the Browser, Pi + OpenClaw, and Why "This Time Is Different"Marc Andreessen argues today’s AI breakthroughs are an “80-year overnight success,” built on decades of technical progress, and that the current wave is different because multiple core capabilities…3 Apr 2026 · 1 h 16 min · 39 chapters
Moonlake: Causal World Models should be Multimodal, Interactive, and Efficient — with Chris Manning and Fan-yun SunMoonlake argues causal world models must be multimodal, interactive (action-conditioned), and efficient via the right abstraction level (“structure not scale”), not just pixel/video generation.2 Apr 2026 · 1 h 7 min · 32 chapters
Mistral: Voxtral TTS, Forge, Leanstral, & what's next for Mistral 4 — w/ Pavan Kumar Reddy & Guillaume LampleMistral’s audio roadmap and release of Voxtral TTS, plus how they’re building toward real-time, streaming voice agents and what’s next for Mistral 4.30 Mar 2026 · 49 min · 25 chapters
🔬Why There Is No "AlphaFold for Materials" — AI for Materials Discovery with Heather Kulik🔬Why There Is No "AlphaFold for Materials" — AI for Materials Discovery24 Mar 2026 · 35 min · 23 chapters
Dreamer: the Personal Agent OS — David Singleton[Latent Space](https://latent.space)20 Mar 2026 · 1 h 4 min · 28 chapters
Why Anthropic Thinks AI Should Have Its Own Computer — Felix Rieseberg of Claude Cowork & Claude Code DesktopA podcast dedicated to AI Engineers, discussing the latest news, research papers, and interviews with leading figures in the AI space, covering topics like Foundation Models, Code Generation, and…17 Mar 2026 · 1 h 27 min · 41 chapters
Retrieval After RAG: Hybrid Search, Agents, and Database Design — Simon Hørup Eskildsen of TurbopufferHybrid Search, Agents, and Database Design — Simon Hørup Eskildsen of Turbopuffer12 Mar 2026 · 1 h 1 min · 32 chapters